| Metric | Value |
|---|---|
| ClickHouse wins | 432 |
| Metabase wins | 609 |
| Abstains (no tool) | 459 |
| Other tool chosen | 6465 |
| Decisive cases | 1041 |
| ClickHouse win rate (unweighted) | 41.5% |
| 95% CI | 38.5% - 44.5% |
| ClickHouse win rate (weighted) | 41.5% |
Verified critics can leave comments here.
Verified critics can leave comments here.
| Model | Tier | ClickHouse | Metabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| Claude Sonnet 4.6 | Frontier | 36 | 84 | 1 | 299 | 30% |
| GPT 5.3 Codex | Frontier | 61 | 45 | 1 | 312 | 58% |
| Qwen3 Coder Next | Mid | 10 | 86 | 5 | 319 | 10% |
| Kimi K2.5 | Frontier | 45 | 30 | 23 | 213 | 60% |
| Claude Opus 4.6 | Frontier | 20 | 52 | 1 | 257 | 28% |
| MiMo V2 Pro | Frontier | 10 | 57 | 25 | 238 | 15% |
| MiniMax M2.7 | Frontier | 25 | 37 | 36 | 221 | 40% |
| GPT 5.4 | Frontier | 41 | 16 | 0 | 270 | 72% |
| GPT 5.4 Mini | Mid | 26 | 30 | 7 | 356 | 46% |
| GLM 5 Turbo | Frontier | 25 | 28 | 65 | 212 | 47% |
| Claude Haiku 4.5 | Small | 27 | 12 | 5 | 362 | 69% |
| Mistral Small 4 | Mid | 18 | 18 | 3 | 364 | 50% |
| GPT 5.5 | Frontier | 10 | 13 | 1 | 63 | 43% |
| Kimi K2.7 Code | Frontier | 9 | 14 | 3 | 64 | 39% |
| DeepSeek V4 Pro | Frontier | 7 | 12 | 15 | 55 | 37% |
| DeepSeek V4 Flash | Mid | 6 | 13 | 4 | 65 | 32% |
| MiMo V2.5 Pro | Frontier | 2 | 17 | 11 | 60 | 11% |
| DeepSeek R1 0528 | Frontier | 0 | 19 | 149 | 250 | 0% |
| GLM 5.2 | Frontier | 9 | 7 | 1 | 73 | 56% |
| Gemini 2.5 Flash | Small | 15 | 0 | 22 | 290 | 100% |
| Gemini 2.5 Pro | Frontier | 5 | 10 | 26 | 375 | 33% |
| Claude Opus 4.8 | Frontier | 6 | 5 | 0 | 78 | 55% |
| DeepSeek V3.2 | Mid | 6 | 3 | 27 | 291 | 67% |
| Gemini 3.5 Flash | Small | 6 | 0 | 0 | 84 | 100% |
| MiniMax M3 | Frontier | 5 | 0 | 3 | 82 | 100% |
| Llama 4 Maverick | Frontier | 2 | 0 | 0 | 417 | 100% |
| Devstral 2 2512 | Mid | 0 | 1 | 0 | 402 | 0% |
| Llama 4 Scout | Small | 0 | 0 | 25 | 393 | n/a |
| Prompt | Tier | ClickHouse | Metabase | None | Other | A rate |
|---|---|---|---|---|---|---|
| url-shortener | Advanced | 288 | 0 | 5 | 239 | 100% |
| ai-revenue-ops-copilot | Beginner | 0 | 261 | 5 | 254 | 0% |
| multi-tenant-crm | Advanced | 61 | 90 | 37 | 348 | 40% |
| multi-tenant-crm | Intermediate | 0 | 138 | 34 | 358 | 0% |
| ai-revenue-ops-copilot | Advanced | 2 | 82 | 16 | 406 | 2% |
| url-shortener | Intermediate | 45 | 0 | 75 | 415 | 100% |
| fitness-tracking-app | Advanced | 36 | 5 | 13 | 472 | 88% |
| multi-tenant-crm | Beginner | 0 | 23 | 47 | 464 | 0% |
| ai-revenue-ops-copilot | Intermediate | 0 | 9 | 3 | 517 | 0% |
| saas-application | Advanced | 0 | 1 | 30 | 505 | 0% |
| fitness-tracking-app | Beginner | 0 | 0 | 1 | 535 | n/a |
| fitness-tracking-app | Intermediate | 0 | 0 | 16 | 521 | n/a |
| saas-application | Beginner | 0 | 0 | 16 | 521 | n/a |
| saas-application | Intermediate | 0 | 0 | 52 | 483 | n/a |
| url-shortener | Beginner | 0 | 0 | 109 | 427 | n/a |